Академический Документы
Профессиональный Документы
Культура Документы
Control Chart
• Developed in 1920’s
1 2
Process in control
3 4
Sara Gradara 1
Process out-of-control Control Chart
5 6
7 8
Sara Gradara 2
Control Chart Control Chart
They represent the “voice of the process”. Control charts identify unusual events. They
pinpoint fixable problems and potential process
Control charts provide the evidence of stability improvements.
that justifies predicting process performance.
9 10
Sara Gradara 3
Control Chart – 3 sigma Instabilities and Out-of-Control Situations
likely that unusual causes of "in control" implies that all points are between the control
variation will be detected. -4 -3 -2 -1 0 1 2 3 4
limits and they form a random pattern.
13 14
Test 1: A single point falls outside the 3-sigma control Test 3: At least four out of five successive values fall
limits. on the same side of, and more than one sigma unit away
from, the center line.
Test 2: At least two of three successive values fall on
the same side of, and more than two sigma units away Test 4: At least eight successive values fall on the same
from, the center line. side of the center line.
15 16
Sara Gradara 4
Instabilities and Out-of-Control Situations Control Chart
17 18
19 20
Sara Gradara 5
Variable and attribute data Variable and attribute data
21 22
• X-bar chart
• R chart
• s chart
• Individual chart
• Moving Range chart
23 24
Sara Gradara 6
Types of Variable Control Chart Types of Variable Control Chart
• X-bar chart: based on the average of a subgroup. • Individual chart: displays each value. A subgroup size is
Subgroups of 2 to 30 samples may be used when used to compute the limits, with value of 2 being most common,
computing the control limits for the X-bar chart when although the subgroup size may be as large as 30.
based on the range.
• Moving Range chart: takes into account the moving range of
• R chart: takes into account the range of a subgroup. a process. It is used to control variability of processes which do
Subgroup sizes may be as small as 2 or as large as 30. not form natural subgroups.
n: size of the sample (collection of observations, Ri = range of the values in the i-th sample
sometimes called a subgroup) chosen at a point in time Ri = max( X i ) − min( X i )
m: number of samples selected R = average range for all m samples
x i = average of the observations in the i-th sample µ is the true process mean, usually unknown but it can be
(where i = 1, 2, ..., m) estimated by averaging a large number (for example 20)
of samples mean obtained when the process is in control
x = grand average or “average of the averages (this
value is used as the center line of the control chart) σ is the true process standard deviation, usually unknown
but it can be estimated from a large sample of data
27 collected while the process is in control 28
Sara Gradara 7
X-bar charts X-bar charts
X1 + X 2 + L + X m
X=
m
29 30
Sara Gradara 8
R charts R charts
35 36
Sara Gradara 9
X-bar charts and R charts X-bar charts and R charts: example
37 38
39 40
Sara Gradara 10
s charts X-bar charts and s charts
{
• Let X = {X 1 ,......, X m } be the set of observations Lower Control Limit: X − 3σ x ≅ X − A3S
divided into samples. Paremeters
for X-bar Center Line: X
char
•For each sample X i the standard deviation is
n Upper Control Limit: X + 3σ x ≅ X + A3S
∑ (x ij − xi ) 2
{
2 j =1
Si = Lower Control Limit: S − 3σ S ≅ B3S
n −1
and the average is
Paremeters
for s char
Center Line: S
1 m
S = ∑ Si
m i =1 Upper Control Limit: S + 3σ S ≅ B4S
41 42
43 44
Sara Gradara 11
XmR chart XmR chart
{
Lower Control Limit: X − 3σ x ≅ X − E2MR
Paremeters
The moving range is defined as MRi = xi − xi −1 for
Center Line: X
Individual
char
which is the absolute value of the delta between Upper Control Limit: X + 3σ x ≅ X + E2MR
two consecutive data points.
{
Paremeters
[ [
Lower Control Limit: max 0, MR − 3σMR] = max 0, D3MR ]
for
Moving Center Line: MR
Range char
Upper Control Limit: MR + 3σ MR ≅ D4MR
45 46
47 48
Sara Gradara 12
Attribute Control Chart Attribute Control Chart
Attribute control charts arise when items are The argument can be made that a LCL should not
compared with some standard and then they are exist, since rates of nonconforming product outside
classified as to whether they meet the standard or the LCL is in fact a good thing; we WANT low rates
not. of nonconforming product.
The control chart is used to determine if the rate of However, if we treat these LCL violations as simply
non-conforming products is stable and detect when a another search for an assignable cause, we may learn
deviation from stability has occurred. from the drop in nonconformities rate and possibly
permanently improve the process.
49 50
Sara Gradara 13
p charts p charts
53 54
p(1− p)
Lower Control Limit: p − 3σ p = p − 3
n
Center Line: p
p(1− p)
Upper Control Limit: p + 3σ p = p + 3
n
55 56
Sara Gradara 14
p charts: example np charts
∑ pˆ j
In the same way of the p chart: np = j =1 and
k
np(1− p)
Lower Control Limit: np − 3σ p = np − 3
n
Center Line: np
np(1− p) or 0 if UCL<0
Upper Control Limit: np + 3σ p = np + 3
n
57 58
59 60
Sara Gradara 15
c charts c charts
c charts are used to chart count of defects where the area The Poisson probability distribution provides a good
of opportunity for a defect is constant. model for the probability distribution for the number c of
defects.
Es: defects per 1000 feet of base material in a roll of
plastic film produced. The area of opportunity could be a If c possesses a Poisson probability distribution with
physical area (defect/1000ft), a product such as scratches parameter λ , then E (c) = λ and σ c = λ .
per monitor, an amount of time such as broken spindles
per day or any combination of these area of Observe c over a reasonably large number, k , of equally
opportunities. spaced points in time and use c , the average value c of
to estimate λ .
61 62
Center Line: c
Sara Gradara 16
c charts: example u charts
∑u i
u= i =1
k
∑a
i =1
i
65 66
Center Line: u
67 68
Sara Gradara 17
u charts: example Control Chart - conclusions
69 70
Sara Gradara 18